© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 9496
    Prev
    Next
    INDEX
    Explanations

    statements related to law enforcement and community relations, especially around issues of police violence and investment strategies

    oai_token-act-pair · gpt-3.5-turbo

    elements related to law enforcement and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mits
    -0.85
     Zot
    -0.82
     Dwarf
    -0.79
     Philipp
    -0.78
     favourites
    -0.77
     Hermes
    -0.77
     Yug
    -0.76
    raft
    -0.76
    ãĤ§
    -0.76
    oeuv
    -0.76
    POSITIVE LOGITS
     policing
    1.57
     DOJ
    1.50
     LAPD
    1.48
     NYPD
    1.44
    erguson
    1.42
     incarceration
    1.42
    police
    1.41
     Violent
    1.40
     crime
    1.39
     homicides
    1.39
    Activations Density 0.717%

    No Known Activations